OpenAIGPT-OSSGptOssForCausalLM

GPT OSS 120B — Hardware Requirements & GPU Compatibility

ChatFunctions

GPT-OSS 120B is the larger of OpenAI's open-source model releases, bringing 120.4 billion parameters of GPT-lineage capability to the open-weight ecosystem. It represents near-frontier performance across reasoning, knowledge, code generation, and conversational tasks, rivaling top proprietary offerings in many benchmarks. Running this model locally is a serious hardware commitment, typically requiring multiple high-VRAM GPUs or a professional-grade setup with 80+ GB of combined VRAM even at aggressive quantization levels. It is best suited for enthusiasts with multi-GPU rigs or workstation hardware who want the strongest possible local model from OpenAI's catalog.

116.8B params · MoE5.8B active131K contextApache 2.0Aug 20253.5M downloads5.4K likes288.2K quant downloads

Your hardware

MacBook Pro 14" M4 Max (128 GB)selected

546 GB/s

Q4_K_M fits · 53.7 GB free · ~61 tok/s · 128K ctx

GPT OSS 120B runs on a 96 GB+ Mac or a workstation GPU

Best local pick → Mac Studio (M3 Ultra, 96GB) · Q4_K_M · 70.8 GB · ~76 tok/s

Macs from 64 GB (~68 tok/s)

Score 97.6#54 of 92 open#23 of 54 that fit ≤96 GBApache 2.0

Not set up for it?

Reference GPU · RTX 4090 24 GB

Estimates, ±20% · how we estimate

AOn your MacBook Pro 14" M4 Max (128 GB): Q4_K_M fits · 53.7 GB free · ~61 tok/s · up to 128K contextMacBook Pro 14" M4 Max (128 GB) page →

llmrun Composite Score →

97.6

90% range 95.3–99.9
#54 of 92 open models
#23 of 54 that fit ≤96 GB

Benchmarks · tier chart ↓

Among 92 open modelsHow the Composite Score is built

Coding97.590% range 93–102
Agents81.590% range 74–89
MathNot enough data yet
Science103.490% range 96–111
Reasoning96.990% range 90–104

Run GPT OSS 120B

Best fit for your MacBook Pro 14" M4 Max (128 GB). Every other method, OS and quant is in the step-by-step guide.

Recommended for your MacBook Pro 14" M4 Max (128 GB)

MLX

one command · needs mlx-lm installed

$mlx_lm.chat --model lmstudio-community/gpt-oss-120b-MLX-8bit

MLX repo with its own quantisation

Download: Q4_K_M/gpt-oss-120b-Q4_K_M-00001-of-00002.gguf62.77 GB + 1 partunsloth

install, OS, other quants

Other ways

each opens step-by-step

Run in cloud

Fits on RTX PRO 6000 (96 GB) (25 GB headroom) · Q4_K_M

Generation speed: ~202 tok/s; generation speed
Cost per 1M output tokens: $2.00; per 1M output tokens

Deployon Vast.aiBest optionfrom $1.45/hr

Compare GPUs →

or

How Much VRAM Does GPT OSS 120B Need?

Select a quantization level; the listed hardware adheres to it.

Quantization	VRAM	+32K	+128K	File	Quality	On your device
	39.8 GB	40.6 GB	43.1 GB	~39.4 GB	2-bit · i-quant medium — Importance-weighted 2-bit, medium	Fits: 128K context · ~81 tok/s
	50.1 GB	50.8 GB	53.4 GB	62.6 GB	2-bit · K-quant — 2-bit quantization with K-quant improvements	Fits: 128K context · ~73 tok/s
	51.5 GB	52.3 GB	54.8 GB	62.6 GB	3-bit small — 3-bit small quantization	Fits: 128K context · ~72 tok/s
	53.0 GB	53.7 GB	56.3 GB	62.7 GB	3-bit · i-quant medium — Importance-weighted 3-bit, medium	Fits: 128K context · ~71 tok/s
	57.4 GB	58.1 GB	60.7 GB	62.6 GB	3-bit medium — 3-bit medium quantization	Fits: 128K context · ~69 tok/s
	58.8 GB	59.6 GB	62.1 GB	62.6 GB	4-bit · legacy — 4-bit legacy quantization	Fits: 128K context · ~68 tok/s
	60.3 GB	61 GB	63.6 GB	62.6 GB	3-bit large — 3-bit large quantization	Fits: 128K context · ~67 tok/s
	63.2 GB	64 GB	66.5 GB	62.7 GB	4-bit · i-quant compact — Importance-weighted 4-bit, compact	Fits: 128K context · ~65 tok/s
	66.1 GB	66.9 GB	69.4 GB	62.7 GB	4-bit · legacy+ — 4-bit legacy quantization with offset	Fits: 128K context · ~64 tok/s
	66.1 GB	66.9 GB	69.4 GB	62.7 GB	4-bit · i-quant non-linear — Importance-weighted 4-bit, non-linear	Fits: 128K context · ~64 tok/s
	66.1 GB	66.9 GB	69.4 GB	62.8 GB	4-bit small — 4-bit small quantization	Fits: 128K context · ~64 tok/s
	70.5 GB	71.3 GB	73.8 GB	62.8 GB	4-bit medium — 4-bit medium quantization — most popular sweet spot	Fits: 128K context · ~61 tok/s
	72.0 GB	72.7 GB	75.3 GB	63.1 GB	4-bit large — 4-bit large quantization	Fits: 128K context · ~61 tok/s
	80.7 GB	81.5 GB	84 GB	62.9 GB	5-bit small — 5-bit small quantization	Fits: 128K context · ~57 tok/s
	83.7 GB	84.4 GB	86.9 GB	62.9 GB	5-bit medium — 5-bit medium quantization — good quality/size tradeoff	Fits: 128K context · ~56 tok/s
	96.8 GB	97.5 GB	100.1 GB	63.3 GB	6-bit, very good — 6-bit quantization, very good quality	Fits: 128K context · ~51 tok/s
	117.2 GB	118 GB	120.5 GB	~116.8 GB	8-bit, near-lossless — 8-bit quantization, near-lossless	Fits: 128K context · ~45 tok/s
	234.1 GB	234.8 GB	237.4 GB	~233.7 GB	16-bit · bfloat — Brain floating point 16 — preferred for training	Does not fit: needs 234.4 GB

Selected Q4_K_M

4-bit medium quantization

70.8GBat 16K context

Weights: 70.1 GB
KV cache: 0.4 GB
Overhead: 0.3 GB

Fits MacBook Pro 14" M4 Max (128 GB) · 53.7 GB free · ~61 tok/s

≥50 tok/s needs ≥296 GB/s · M3 Ultra ~76, M2 Ultra ~75

Or rent RTX PRO 6000 from $1.45/hr.

Which Hardware Can Run GPT OSS 120B?

Q4_K_M · 70.5 GB

GPT OSS 120B (Q4_K_M) requires 70.5 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 92+ GB is recommended. Using the full 131K context window can add up to 3.3 GB, bringing total usage to 73.8 GB. No consumer GPU has enough memory. 33 devices with unified memory can run GPT OSS 120B, including NVIDIA DGX H100, NVIDIA DGX A100 640GB, Mac Studio (M3 Ultra, 96GB).

By VRAM tier · typical GPUs and Macs at Q4_K_M

Typical hardwareQuantVRAMtok/sContext that fits

8–16 GB · RTX 4060, RTX 3060 12GB, RTX 5060 Ti 16GBDoesn't fit — smallest quant needs 40.2 GB8 GB tier →12 GB tier →16 GB tier →

24 GB · RTX 4090referenceDoesn't fit — smallest quant needs 40.2 GB24 GB tier →

Mac 32 GB · Mac Mini M4Doesn't fit — smallest quant needs 40.2 GBMacs →

Mac 64 GB · Mac Studio M4 MaxQ4_0 · 59.1 GB · ~68 tok/s · 64K59.1~6864KMacs →

How good is GPT OSS 120B?

The llmrun Score merges 20 public benchmark boards into a single figure, where 100 represents the average for open models.

Score vs VRAM in the ≤96 GB tier

GPT OSS 120B
Other models
Best Score for its VRAM
x: VRAM (GB, log scale) · y: llmrun Score

#23 of 54 that fit ≤96 GBEvery model here fits your MacBook Pro 14" M4 Max (128 GB) (128 GB)

Each dot is a model at the best quant that fits ≤96 GB. The line joins the models with the best Score for their VRAM; a dot below it is beaten by a model that needs no more memory.

Full ≤96 GB ranking →

Benchmarks

SWE-bench Verified
SWE-bench · Aug 2025Independent
26.0%
#20/20 open
Independent
GPQA Diamond
Epoch AI · Aug 2025Independent
75.8%
#28/97 open
Independent
LMArena Text
LMArena · Oct 2026Arena
1351.8
#74/186 open
Arena
AIME 2024/2025
Epoch AI · Aug 2025Independent
88.9%
#14/85 open
Independent
Terminal-Bench
Epoch AI · Aug 2025Lab-reported
18.7%
#14/16 open
Lab-reported
MMLU-Pro
TIGER-LabIndependent
80.8%
#23/144 open
Independent

All 21 GPT OSS 120B benchmarks

In the ≤96 GB class

54 models fit ≤96 GB

Same Score, only models that fit ≤96 GB at their best quant: the ranking a ≤96 GB owner actually chooses from.

#1
DeepSeek V4 Flash 0731DeepSeek
127.6
~103 tok/s · 95.5 GB
#2
Qwen3.8 27BAlibaba
121.5
~67 tok/s · 17.9 GB
#3
Inkling SmallThinking Machines
119.4
~356 tok/s · 92.9 GB
#4
MiniMax M2.5MiniMax
111.8
~138 tok/s · 93.9 GB
#5
Qwen3.6 27BAlibaba
111.4
~67 tok/s · 17.9 GB
#6
Qwen3.5 122B A10BAlibaba
109.4
~108 tok/s · 75.5 GB

Full ≤96 GB ranking →RTX PRO 6000 Blackwell Workstation Edition page →

Alternatives to GPT OSS 120B

GPT-OSS family · 14 models →

Official models with an llmrun Score, each answering one question; numbers are at the best quant that fits a 24 GB GPU.

Similar models

10tok/s on RTX 4090

Model	Score	VRAM	tok/s	Why it is similar
MiniMax M2.5MiniMax	111.8	139.6 GB	—needs > 24 GB	similar score
Qwen3.5 122B A10BAlibaba	109.4	75.5 GB	—needs > 24 GB	similar score
MiniMax M2MiniMax	104.0	139.6 GB	—needs > 24 GB	similar score
Qwen3 32BAlibaba	98.4	22.6 GB	~32	similar score
DeepSeek R1 Distill Qwen 32BDeepSeek	97.0	23 GB	~34	similar score
Qwen3 30B A3B Instruct 2507Alibaba	96.5	19.4 GB	~173	similar score
NVIDIA Nemotron 3 Super 120B A12B BF16NVIDIA	95.8	74.7 GB	—needs > 24 GB	similar score
Llama 4 Scout 17B 16E InstructMeta	81.8	77 GB	—needs > 24 GB	same size
Mistral Large Instruct 2407Mistral AI	81.1	86.4 GB	—needs > 24 GB	same size
Mixtral 8x22B Instruct v0.1Mistral AI	71.6	88.4 GB	—needs > 24 GB	same size

Fine-tunes & variants(8)community builds of GPT OSS 120B

Specifications

Publisher: OpenAI
Family: GPT-OSS
Parameters: 116.8B
Active parameters: 5.8B per token
Architecture: GptOssForCausalLM
Context Length: 131,072 tokens
Vocabulary Size: 201,088
Release Date: 2025-08-04
License: Apache 2.0

Resources

Frequently Asked Questions

How much VRAM does GPT OSS 120B need?

GPT OSS 120B requires 70.5 GB of VRAM at Q4_K_M, or 234.1 GB at BF16. Full 131K context adds up to 3.3 GB (73.8 GB total).

VRAM = Weights + KV Cache + Overhead

Weights = 116.8B × 4.8 bits ÷ 8 = 70.1 GB

KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)

Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.

KV Cache + Overhead ≈ 3.7 GB (at full 131K context)

VRAM usage by quantization

Q4_K_M

70.5 GB

Q4_K_M + full context

73.8 GB

Learn more about VRAM estimation →

Can NVIDIA GeForce RTX 5090 run GPT OSS 120B?

No — GPT OSS 120B requires at least 39.8 GB at IQ2_M, which exceeds the NVIDIA GeForce RTX 5090's 32 GB of VRAM.

What's the best quantization for GPT OSS 120B?

For GPT OSS 120B, Q4_K_M (70.5 GB) offers the best balance of quality and VRAM usage. Q4_K_L (72.0 GB) provides better quality if you have the VRAM. The smallest option is IQ2_M at 39.8 GB.

VRAM requirement by quantization

IQ2_M

39.8 GB~62%

Q3_K_M

57.4 GB~83%

IQ4_NL

66.1 GB~88%

Q4_K_M ★

70.5 GB~89%

Q5_K_S

80.7 GB~92%

BF16

234.1 GB~100%

★ Recommended — best balance of quality and VRAM usage.

Learn more about quantization →

Can I run GPT OSS 120B on a Mac?

Yes, but only at lower quantizations. The smallest Mac that can run GPT OSS 120B is Mac Mini M4 Pro (48 GB) at IQ2_M; 56 of the 156 Macs we list can run it at some quantization. For Q4_K_M (70.5 GB) you need a Mac with more unified memory.

Can I run GPT OSS 120B locally?

Yes — GPT OSS 120B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.

How fast is GPT OSS 120B?

At Q4_K_M, GPT OSS 120B can reach ~126 tok/s on AMD Instinct MI350X. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.

tok/s = 1000 ÷ (active GB ÷ (bandwidth GB/s × efficiency) × 1000 + layers × routing ms)

Mixture-of-Experts: just the active experts get read for each token, along with a fixed routing cost per layer.

Example: NVIDIA B200 → 3.5 GB active ÷ (8000 × 0.65) = 0.667 ms, plus 36 layers × 0.055 ms = 1.980 ms, so 1000 ÷ 2.647 ms = ~378 tok/s

Estimated speed at Q4_K_M (70.5 GB)

NVIDIA B200

~378 tok/s

NVIDIA B300

~378 tok/s

NVIDIA GH200 Grace Hopper Superchip

~326 tok/s

Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.

Learn more about tok/s estimation →

What's the download size of GPT OSS 120B?

At Q4_K_M, the download is about 70.10 GB. The full-precision BF16 version is 233.66 GB. The smallest option (IQ2_M) is 39.43 GB.

Which GPUs can run GPT OSS 120B?

No single consumer GPU has enough VRAM to run GPT OSS 120B at Q4_K_M (70.5 GB). Multi-GPU or professional hardware is required.

Which devices can run GPT OSS 120B?

33 devices with unified memory can run GPT OSS 120B at Q4_K_M (70.5 GB), including ASUS Ascent GX10, Asus ROG Flow Z13 (2025, Ryzen AI Max+ 395, 128 GB), Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.

Run GPT OSS 120B

70.8 GB memory at 16K context · fits your MacBook Pro 14" M4 Max (128 GB) (53.7 GB free)

Works on macOS, Windows and Linux.

Install Ollama (Linux)
$curl -fsSL https://ollama.com/install.sh | sh
Install Ollama (macOS / Windows)
Download and run the app; it installs the ollama command.
Download Ollama ↗
Run Q4_K_M
$ollama run hf.co/unsloth/gpt-oss-120b-GGUF:Q4_K_M
Raise the context window
Type it inside the chat. For the API server instead, start it with OLLAMA_CONTEXT_LENGTH=16384 ollama serve.
$/set parameter num_ctx 16384
A larger context needs more memory than the weights alone.
Use the API
Ollama serves its API on http://localhost:11434.

Works on macOS, Windows and Linux.

Install LM Studio
Desktop app for macOS (Apple silicon), Windows and Linux.
lmstudio.ai ↗
Download the model
In the app press Ctrl/Cmd + Shift + M and paste https://huggingface.co/unsloth/gpt-oss-120b-GGUF, then pick Q4_K_M. Or use the CLI (run LM Studio once first):
$lms get https://huggingface.co/unsloth/gpt-oss-120b-GGUF@Q4_K_M
Open on Hugging Face ↗
Load and chat
Open the model loader, select the model and set Context Length to 16384. Leave GPU offload at maximum if it fits.
Start the local server (optional)
$lms server start

Works on macOS, Windows and Linux.

Install llama.cpp (macOS)
MacPorts, Nix and conda-forge also work.
$brew install llama.cpp
Install options ↗
Install llama.cpp (Windows)
$winget install llama.cpp
Install llama.cpp (Linux)
Download the prebuilt llama-*-bin-ubuntu-* archive for your GPU backend (CPU, Vulkan) from the releases page, unpack it and run the binaries from that folder. Homebrew (brew install llama.cpp) and conda-forge also work on Linux.
llama.cpp releases ↗
Start the server
Downloads the model on first run. The chat UI and an OpenAI-compatible API are at http://localhost:8080.
$llama-server -hf unsloth/gpt-oss-120b-GGUF:Q4_K_M -c 16384 -ngl 99 --port 8080

Works on macOS, Windows and Linux.

Option A: Docker Model Runner
Docker Desktop: Settings > AI > Enable Docker Model Runner. Docker Engine on Linux: install the docker-model-plugin package.
$docker model run hf.co/unsloth/gpt-oss-120b-GGUF:Q4_K_M
Model Runner docs ↗
The quant tag after the repo is how Hugging Face cards write it; if your Docker version rejects it, drop the tag and pick the quant by repo.
Option B: llama.cpp server image (NVIDIA)
Needs the NVIDIA Container Toolkit. Models are cached in the llama-cache volume. Open http://localhost:8080.
$docker run --gpus all -p 8080:8080 -v llama-cache:/root/.cache ghcr.io/ggml-org/llama.cpp:server-cuda -hf unsloth/gpt-oss-120b-GGUF:Q4_K_M -c 16384 -ngl 99 --host 0.0.0.0 --port 8080
Image tags (cuda13, vulkan, rocm) ↗
Cache path inside the image is not in the docs; remove the -v flag if the volume complains.

macOS only.

Install mlx-lm
$pip install mlx-lm
Chat in the terminal
$mlx_lm.chat --model lmstudio-community/gpt-oss-120b-MLX-8bit
Downloads the model on first run. The MLX repo has its own quantisation; it may not match the quant selected above.
Or start a local server
Listens on http://localhost:8080.
$mlx_lm.server --model lmstudio-community/gpt-oss-120b-MLX-8bit

Works on macOS, Windows and Linux.

Install Jan
jan.ai ↗
Find the model
Open the Hub tab, paste this model ID in Search, and choose Q4_K_M if offered.
$unsloth/gpt-oss-120b-GGUF
Use the local API (optional)
Settings > Local API Server > Start Server. It listens on http://127.0.0.1:1337.

Rent GPUs hourly to run Q4_K_M right there. Pricing comes from partner marketplaces and varies.

Available GPU rentals for Q4_K_M, prioritized by value
GPU	Speed	$/1M tokens	Rent
RTX PRO 6000 Max-Q (96 GB)CheapestCheapest25 GB free	~202 tok/s	$2.00	Deploy on Vast.aifrom $1.45/hr (opens in new tab)	96 GB · 25 GB free · ~202 tok/s · $2.00 / 1M tokens
RTX PRO 6000 Server (96 GB)25 GB free	~188 tok/s	$2.28	Deploy on Vast.aifrom $1.54/hr (opens in new tab)	96 GB · 25 GB free · ~188 tok/s · $2.28 / 1M tokens
RTX PRO 6000 (96 GB)25 GB free	~202 tok/s	$2.21	Deploy on Vast.aifrom $1.60/hr (opens in new tab)	96 GB · 25 GB free · ~202 tok/s · $2.21 / 1M tokens
RTX PRO 6000 (96 GB)25 GB free	~202 tok/s	$2.33	Deploy on RunPodfrom $1.69/hr (opens in new tab)	96 GB · 25 GB free · ~202 tok/s · $2.33 / 1M tokens
RTX PRO 6000 Server (96 GB)25 GB free	~188 tok/s	$2.50	Deploy on RunPodfrom $1.69/hr (opens in new tab)	96 GB · 25 GB free · ~188 tok/s · $2.50 / 1M tokens
H200 SXM (141 GB)70 GB free	~323 tok/s	$3.08	Deploy on RunPodfrom $3.59/hr (opens in new tab)	141 GB · 70 GB free · ~323 tok/s · $3.08 / 1M tokens
H200 NVL (141 GB)70 GB free	~323 tok/s	$4.01	Deploy on Vast.aifrom $4.67/hr (opens in new tab)	141 GB · 70 GB free · ~323 tok/s · $4.01 / 1M tokens
B200 (192 GB)121 GB free	~378 tok/s	$4.40	Deploy on RunPodfrom $5.98/hr (opens in new tab)	192 GB · 121 GB free · ~378 tok/s · $4.40 / 1M tokens

Compare GPUs →